v1v2 (latest)

Understanding the Curse of Horizon in Off-Policy Evaluation via Conditional Importance Sampling

International Conference on Machine Learning (ICML), 2019

15 October 2019

Pierre-Luc Bacon

Papers citing "Understanding the Curse of Horizon in Off-Policy Evaluation via Conditional Importance Sampling"

33 / 33 papers shown

Title
STITCH-OPE: Trajectory Stitching with Guided Diffusion for Off-Policy Evaluation Hossein Goli Michael Gimelfarb Nathan Samuel de Lara Haruki Nishimura Masha Itkina Florian Shkurti OffRL 199 1 0 27 May 2025
DOLCE: Decomposing Off-Policy Evaluation/Learning into Lagged and Current Effects Shu Tamano Masanori Nojima OffRL 360 0 0 02 May 2025
When Machine Learning Meets Importance Sampling: A More Efficient Rare Event Estimation Approach Ruoning Zhao Xinyun Chen 91 0 0 18 Apr 2025
Concept-driven Off Policy Evaluation Ritam Majumdar Jack Teversham Sonali Parbhoo OffRL 280 0 0 28 Nov 2024
POTEC: Off-Policy Learning for Large Action Spaces via Two-Stage Policy Decomposition Yuta Saito Jihan Yao Thorsten Joachims OffRL 201 11 0 09 Feb 2024
Conservative Exploration for Policy Optimization via Off-Policy Policy Evaluation Paul Daoudi Mathias Formoso Othman Gaizi Achraf Azize Evrard Garcelon OffRL 172 0 0 24 Dec 2023
Marginal Density Ratio for Off-Policy Evaluation in Contextual BanditsNeural Information Processing Systems (NeurIPS), 2023 Muhammad Faaiz Taufiq Arnaud Doucet Rob Cornish Jean-François Ton OffRL 222 9 0 03 Dec 2023
Off-Policy Evaluation for Human FeedbackNeural Information Processing Systems (NeurIPS), 2023 Qitong Gao Ge Gao Juncheng Dong Vahid Tarokh Min Chi Miroslav Pajic OffRL 270 7 0 11 Oct 2023
Stackelberg Batch Policy Learning Wenzhuo Zhou Annie Qu OffRL 182 1 0 28 Sep 2023
Hindsight-DICE: Stable Credit Assignment for Deep Reinforcement Learning Akash Velu Skanda Vaidyanath Dilip Arumugam OffRL 216 2 0 21 Jul 2023
Value-aware Importance Weighting for Off-policy Reinforcement Learning Kristopher De Asis Eric Graves R. Sutton OffRL 118 2 0 27 Jun 2023
Off-Policy Evaluation for Large Action Spaces via Conjunct Effect ModelingInternational Conference on Machine Learning (ICML), 2023 Yuta Saito Qingyang Ren Thorsten Joachims CML OffRL 234 30 0 14 May 2023
Model-based Offline Reinforcement Learning with Local MisspecificationAAAI Conference on Artificial Intelligence (AAAI), 2023 Kefan Dong Yannis Flet-Berliac Allen Nie Emma Brunskill OffRL 156 6 0 26 Jan 2023
Scaling Marginalized Importance Sampling to High-Dimensional State-Spaces via State AbstractionAAAI Conference on Artificial Intelligence (AAAI), 2022 Brahma S. Pavse Josiah P. Hanna OffRL 156 8 0 14 Dec 2022
A Review of Off-Policy Evaluation in Reinforcement Learning Masatoshi Uehara C. Shi Nathan Kallus OffRL 202 99 0 13 Dec 2022
Low Variance Off-policy Evaluation with State-based Importance SamplingConference on Algebraic Informatics (AI), 2022 David M. Bossens Philip S. Thomas OffRL 333 3 0 07 Dec 2022
Estimating Time-Varying Direct and Indirect Causal Excursion Effects with Longitudinal Binary Outcomes Jieru Shi Zhanghua Wu Walter Dempsey CML 65 1 0 02 Dec 2022
Marginalized Operators for Off-policy Reinforcement LearningInternational Conference on Artificial Intelligence and Statistics (AISTATS), 2022 Yunhao Tang Mark Rowland Rémi Munos Michal Valko OffRL 136 0 0 30 Mar 2022
Importance Sampling Placement in Off-Policy Temporal-Difference Methods Eric Graves Sina Ghiassian OffRL 163 2 0 18 Mar 2022
Off-Policy Evaluation for Large Action Spaces via EmbeddingsInternational Conference on Machine Learning (ICML), 2022 Yuta Saito Thorsten Joachims OffRL 192 55 0 13 Feb 2022
Flexible Option LearningNeural Information Processing Systems (NeurIPS), 2021 Martin Klissarov Doina Precup OffRL 123 31 0 06 Dec 2021
SOPE: Spectrum of Off-Policy Estimators C. J. Yuan Yash Chandak S. Giguere Philip S. Thomas S. Niekum OffRL 209 5 0 06 Nov 2021
Adaptive Importance Sampling meets Mirror Descent: a Bias-variance tradeoffInternational Conference on Artificial Intelligence and Statistics (AISTATS), 2021 Anna Korba Franccois Portier 181 16 0 29 Oct 2021
A Deep Reinforcement Learning Approach to Marginalized Importance Sampling with the Successor RepresentationInternational Conference on Machine Learning (ICML), 2021 Scott Fujimoto David Meger Doina Precup 139 17 0 12 Jun 2021
Universal Off-Policy EvaluationNeural Information Processing Systems (NeurIPS), 2021 Yash Chandak S. Niekum Bruno C. da Silva Erik Learned-Miller Emma Brunskill Philip S. Thomas OffRL ELM 232 57 0 26 Apr 2021
Non-asymptotic Confidence Intervals of Off-policy Evaluation: Primal and Dual BoundsInternational Conference on Learning Representations (ICLR), 2021 Yihao Feng Ziyang Tang Na Zhang Qiang Liu OffRL 166 14 0 09 Mar 2021
Instabilities of Offline RL with Pre-Trained Neural RepresentationInternational Conference on Machine Learning (ICML), 2021 Ruosong Wang Yifan Wu Ruslan Salakhutdinov Sham Kakade OffRL 239 43 0 08 Mar 2021
Near-Optimal Offline Reinforcement Learning via Double Variance ReductionNeural Information Processing Systems (NeurIPS), 2021 Ming Yin Yu Bai Yu Wang OffRL 188 70 0 02 Feb 2021
What are the Statistical Limits of Offline RL with Linear Function Approximation? Ruosong Wang Dean Phillips Foster Sham Kakade OffRL 329 168 0 22 Oct 2020
CoinDICE: Off-Policy Confidence Interval Estimation Bo Dai Ofir Nachum Yinlam Chow Lihong Li Csaba Szepesvári Dale Schuurmans OffRL 204 89 0 22 Oct 2020
Off-policy Evaluation in Infinite-Horizon Reinforcement Learning with Latent ConfoundersInternational Conference on Artificial Intelligence and Statistics (AISTATS), 2020 Andrew Bennett Nathan Kallus Lihong Li Ali Mousavi OffRL 147 45 0 27 Jul 2020
Statistically Efficient Off-Policy Policy GradientsInternational Conference on Machine Learning (ICML), 2020 Nathan Kallus Masatoshi Uehara OffRL 227 40 0 10 Feb 2020
Minimax Value Interval for Off-Policy Evaluation and Policy Optimization Nan Jiang Jiawei Huang OffRL 331 17 0 06 Feb 2020